Open Source

Step-Audio-R1

Step-Audio-R1 is the first audio language model to successfully unlock Chain-of-Thought (CoT) reasoning.

Source: GitHub Pricing: Open Source
💻 View Code

About This Project

Step-Audio-R1 introduces Modality-Grounded Reasoning Distillation (MGRD) to shift reasoning from textual abstractions directly to acoustic properties. This allows it to perform complex Chain-of-Thought reasoning for audio, solving the 'inverted scaling' problem seen in prior models.

Tags

audio-language-model audio-reasoning chain-of-thought

Installation & Setup

git lfs install
git clone https://huggingface.co/stepfun-ai/Step-Audio-R1

Reviews & Ratings

Share your experience

User Reviews (0)

No reviews yet. Be the first to share your experience!